bykarryviber· 33 skills
非琐碎任务开工前显式化「我的解读 / 隐含假设 / 已知 tradeoff / 倾向方案」让 Karry 拦截;收工时同等显式化「这次牺牲了什么 / 高风险点要不要派 attacker 二次攻击」。Use when 任务 ≥3 步、含歧义解读、涉及 tradeoff、用户指令模糊有多种合理解读,或非琐碎任务即将收尾出结论。短指令作用层判定走 terse-intent-classifier。
$npx -y skills add karryviber/orb --skill state-assumptions-before-actingInstalls into the current project.
Run `npx skills use "https://github.com/karryviber/orb" --skill "karryviber/orb/state-assumptions-before-acting"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/karryviber/orb" that are relevant to the current task. Run `npx skills add "https://github.com/karryviber/orb"` and select the relevant skills, then follow their instructions.